© The Hong Kong Polytechnic University

DEPARTMENT OF LOGISTICS AND MARITIME STUDIES

Student Name:

Student Number:

MSc in Management (Operations Management)

Programme Code : 44085/44086

Session : Semester 1, 2016/2017 Subject Code : LGT5158

Subject Title : Statistical Quality Control for Manufacturing and Service

Time : 1900-2200 Time allowed : 3 hours

This question paper has a total of ____4____ pages (including this covering page).

Instructions to Candidates: It is an OPEN-BOOK examination.

This paper contains FIVE questions.

Answer any FOUR questions on the answer book. All questions

Let the invigilator know if you need additional paper.

Non-programmable calculators are allowed.

Computers and mobile phones are NOT allowed.

This question book will be collected at the end of the exam.

Available from Invigilator : Nil

DO NOT TURN OVER THE PAGE UNTIL YOU ARE TOLD TO DO SO.
 © The Hong Kong Polytechnic University

2016/17, Sem 1

Question 1

(a) Quality costs are widely used by organizations to evaluate and improve quality
performance. Outline the four categories of quality related costs.
(8 marks)

(b) Explain how statistical process control supports the Deming’s philosophy.
(7 marks)

(c) Discuss the preliminary decisions that must be made before you construct control
charts.
(10 marks)

Question 2

(a) An inspector visually inspects 200 sheets of paper for aesthetics. Using trained
judgment, the inspector will either accept or reject sheets based on whether they
are flawless. Following are the results of recent inspections:

Sample Defectives Sample Defectives

1 10 6 3
2 15 7 10
3 12 8 14
4 14 9 12
5 26 10 11

(i) Given these results, using a p chart, determine if the process is stable.
(ii) What would need to be done to improve the process?
(iii) Compute the limits for an np chart.
(20 marks)

(b) Explain why it is important that changes in the operations must be documented in
detail during the implementation of statistical process control.
(5 marks)

LGT5158/Statistical Quality Control for Manufacturing and Service Page 2 of 4

2016/17, Sem 1

Question 3

(a) Control charts for x and R are to be established to control the tensile strength in
pounds of a metal part. Thirty samples of size n = 5 parts are collected over a
period of time with the following results:
30 30

∑ xi = 607.8
i =1
and ∑R
i =1
i = 144

(i) Determine the centrelines and control limits for x and R control charts.
(ii) Suppose both charts exhibit control. There is a single lower specification
limit of 16 lb. If strength is normally distributed, what fraction of metal
part would fail to meet specification?
(17 marks)
(b) Describe the differences between an attribute control chart and a variable control
chart. What are the advantages and disadvantages of using variables rather than
attributes in control charts?
(8 marks)

Question 4

(a) In a factory, the probability that the screen of a LCD monitor with dimensions
30 cm x 40 cm produced has a dot defect for every 10 cm x 10 cm region is 0.1.
The screen of a LCD monitor can be divided into 12 regions with dimensions of
10 cm x 10 cm. It is given that there is at most 1 dot defect for every 10 cm x 10
cm region.
(i) Find the probabilities of the following events.
I. A LCD monitor has no dot defect.
II. A LCD monitor has exactly 1 dot defect.
III. A LCD monitor has more than 2 dot defects.
(ii) For every batch, 6 LCD monitors are chosen at random for quality control
testing. If a batch contains 4 LCD monitors with each has more than 2 dot
defects, the batch will be rejected. Find the probability that exactly 2 LCD
monitors have more than 2 dot defects in a batch.
(15 marks)
(b) Give a brief account of the following terms:
(i) Average Outgoing Quality Limit
(ii) Natural Tolerance Limits
(10 marks)

LGT5158/Statistical Quality Control for Manufacturing and Service Page 3 of 4

2016/17, Sem 1

Question 5

(a) Explain the differences between specification limits and control limits.
(8 marks)

(b) A project team in a small bank was studying the productivity of the operations.
The variation in transaction times had been identified as a potential area for
improvement. 24 samples of size n = 7 are collected over a period of time with the
following results:
24 24

∑ xi = 5640 seconds
i =1
and ∑R
i =1
i = 1900 seconds

Control limits for x and R control charts were calculated and process was shown to
be stable. An “efficiency standard” had been laid down that transactions should be
on average at 3 minutes, with a maximum of 5 minutes for any one transaction.
(i) Estimate the process parameters from the control charts.
(ii) Find an appropriate capability index and comment.
(12 marks)

(c) Explain why process capability should only be addressed when the process is
considered statistically under control.
(5 marks)

~ END ~

LGT5158/Statistical Quality Control for Manufacturing and Service Page 4 of 4